[Tarantool-patches] [PATCH v27 2/3] qsync: order access to the limbo terms

Cyrill Gorcunov gorcunov at gmail.com
Thu Dec 30 23:23:46 MSK 2021


Limbo terms tracking is shared between appliers and when
one of appliers is waiting for write to complete inside
journal_write() routine, an other may need to access read
term value to figure out if promote request is valid to
apply. Due to cooperative multitasking access to the terms
is not consistent so we need to be sure that other fibers
read up to date terms (ie written to the WAL).

For this sake we use a latching mechanism, when one fiber
takes a lock for updating other readers are waiting until
the operation is complete.

For example here is a call graph of two appliers

applier 1
---------
applier_apply_tx
  (promote term = 3
   current max term = 2)
  applier_synchro_filter_tx
  apply_synchro_row
    journal_write
      (sleeping)

at this moment another applier comes in with obsolete
data and term 2

                              applier 2
                              ---------
                              applier_apply_tx
                                (term 2)
                                applier_synchro_filter_tx
                                  txn_limbo_is_replica_outdated -> false
                                journal_write (sleep)

applier 1
---------
journal wakes up
  apply_synchro_row_cb
    set max term to 3

So the applier 2 didn't notice that term 3 is already seen
and wrote obsolete data. With locking the applier 2 will
wait until applier 1 has finished its write.

We introduce the following helpers:

1) txn_limbo_begin: which takes a lock
2) txn_limbo_commit and txn_limbo_rollback which simply release
   the lock but have different names for better semantics
3) txn_limbo_process is a general function which uses x_begin
   and x_commit helper internally
4) txn_limbo_apply to do a real job over processing the
   request, it implies that txn_limbo_begin been called

Testing such in-flight condition won't be easy so we introduce
"box.info.synchro.queue.waiters" field which represent current
number of fibers waiting for limbo to finish request processing.

@TarantoolBot document
Title: synchronous replication changes

`box.info.synchro.queue` gets a new field: `waiters`. It represents
current number of fibers waiting the synchronous transaction processing
to complete.

Part-of #6036

Signed-off-by: Cyrill Gorcunov <gorcunov at gmail.com>
---
 src/box/applier.cc  | 12 ++++++++---
 src/box/lua/info.c  |  4 +++-
 src/box/txn_limbo.c | 18 ++++++++++++++--
 src/box/txn_limbo.h | 52 ++++++++++++++++++++++++++++++++++++++++-----
 4 files changed, 75 insertions(+), 11 deletions(-)

diff --git a/src/box/applier.cc b/src/box/applier.cc
index dd66ef3fa..f09b346a0 100644
--- a/src/box/applier.cc
+++ b/src/box/applier.cc
@@ -866,7 +866,7 @@ apply_synchro_row_cb(struct journal_entry *entry)
 		applier_rollback_by_wal_io(entry->res);
 	} else {
 		replica_txn_wal_write_cb(synchro_entry->rcb);
-		txn_limbo_process(&txn_limbo, synchro_entry->req);
+		txn_limbo_apply(&txn_limbo, synchro_entry->req);
 		trigger_run(&replicaset.applier.on_wal_write, NULL);
 	}
 	fiber_wakeup(synchro_entry->owner);
@@ -882,6 +882,8 @@ apply_synchro_row(uint32_t replica_id, struct xrow_header *row)
 	if (xrow_decode_synchro(row, &req) != 0)
 		goto err;
 
+	txn_limbo_begin(&txn_limbo);
+
 	struct replica_cb_data rcb_data;
 	struct synchro_entry entry;
 	/*
@@ -919,12 +921,16 @@ apply_synchro_row(uint32_t replica_id, struct xrow_header *row)
 	 * transactions side, including the async ones.
 	 */
 	if (journal_write(&entry.base) != 0)
-		goto err;
+		goto err_rollback;
 	if (entry.base.res < 0) {
 		diag_set_journal_res(entry.base.res);
-		goto err;
+		goto err_rollback;
 	}
+	txn_limbo_commit(&txn_limbo);
 	return 0;
+
+err_rollback:
+	txn_limbo_rollback(&txn_limbo);
 err:
 	diag_log();
 	return -1;
diff --git a/src/box/lua/info.c b/src/box/lua/info.c
index 8e02f6594..274b0b047 100644
--- a/src/box/lua/info.c
+++ b/src/box/lua/info.c
@@ -637,11 +637,13 @@ lbox_info_synchro(struct lua_State *L)
 
 	/* Queue information. */
 	struct txn_limbo *queue = &txn_limbo;
-	lua_createtable(L, 0, 2);
+	lua_createtable(L, 0, 3);
 	lua_pushnumber(L, queue->len);
 	lua_setfield(L, -2, "len");
 	lua_pushnumber(L, queue->owner_id);
 	lua_setfield(L, -2, "owner");
+	lua_pushnumber(L, queue->promote_latch_cnt);
+	lua_setfield(L, -2, "waiters");
 	lua_setfield(L, -2, "queue");
 
 	return 1;
diff --git a/src/box/txn_limbo.c b/src/box/txn_limbo.c
index 70447caaf..5eb6ee61d 100644
--- a/src/box/txn_limbo.c
+++ b/src/box/txn_limbo.c
@@ -47,6 +47,8 @@ txn_limbo_create(struct txn_limbo *limbo)
 	vclock_create(&limbo->vclock);
 	vclock_create(&limbo->promote_term_map);
 	limbo->promote_greatest_term = 0;
+	latch_create(&limbo->promote_latch);
+	limbo->promote_latch_cnt = 0;
 	limbo->confirmed_lsn = 0;
 	limbo->rollback_count = 0;
 	limbo->is_in_rollback = false;
@@ -724,11 +726,14 @@ txn_limbo_wait_empty(struct txn_limbo *limbo, double timeout)
 }
 
 void
-txn_limbo_process(struct txn_limbo *limbo, const struct synchro_request *req)
+txn_limbo_apply(struct txn_limbo *limbo,
+		const struct synchro_request *req)
 {
+	assert(latch_is_locked(&limbo->promote_latch));
+
 	uint64_t term = req->term;
 	uint32_t origin = req->origin_id;
-	if (txn_limbo_replica_term(limbo, origin) < term) {
+	if (vclock_get(&limbo->promote_term_map, origin) < (int64_t)term) {
 		vclock_follow(&limbo->promote_term_map, origin, term);
 		if (term > limbo->promote_greatest_term)
 			limbo->promote_greatest_term = term;
@@ -786,6 +791,15 @@ txn_limbo_process(struct txn_limbo *limbo, const struct synchro_request *req)
 	return;
 }
 
+void
+txn_limbo_process(struct txn_limbo *limbo,
+		  const struct synchro_request *req)
+{
+	txn_limbo_begin(limbo);
+	txn_limbo_apply(limbo, req);
+	txn_limbo_commit(limbo);
+}
+
 void
 txn_limbo_on_parameters_change(struct txn_limbo *limbo)
 {
diff --git a/src/box/txn_limbo.h b/src/box/txn_limbo.h
index 53e52f676..42d572595 100644
--- a/src/box/txn_limbo.h
+++ b/src/box/txn_limbo.h
@@ -31,6 +31,7 @@
  */
 #include "small/rlist.h"
 #include "vclock/vclock.h"
+#include "latch.h"
 
 #include <stdint.h>
 
@@ -147,6 +148,14 @@ struct txn_limbo {
 	 * limbo and raft are in sync and the terms are the same.
 	 */
 	uint64_t promote_greatest_term;
+	/**
+	 * To order access to the promote data.
+	 */
+	struct latch promote_latch;
+	/**
+	 * Latch owners/waiters stat.
+	 */
+	uint64_t promote_latch_cnt;
 	/**
 	 * Maximal LSN gathered quorum and either already confirmed in WAL, or
 	 * whose confirmation is in progress right now. Any attempt to confirm
@@ -216,7 +225,7 @@ txn_limbo_last_entry(struct txn_limbo *limbo)
  * @a replica_id.
  */
 static inline uint64_t
-txn_limbo_replica_term(const struct txn_limbo *limbo, uint32_t replica_id)
+txn_limbo_replica_term(struct txn_limbo *limbo, uint32_t replica_id)
 {
 	return vclock_get(&limbo->promote_term_map, replica_id);
 }
@@ -226,11 +235,14 @@ txn_limbo_replica_term(const struct txn_limbo *limbo, uint32_t replica_id)
  * data from it. The check is only valid when elections are enabled.
  */
 static inline bool
-txn_limbo_is_replica_outdated(const struct txn_limbo *limbo,
+txn_limbo_is_replica_outdated(struct txn_limbo *limbo,
 			      uint32_t replica_id)
 {
-	return txn_limbo_replica_term(limbo, replica_id) <
-	       limbo->promote_greatest_term;
+	latch_lock(&limbo->promote_latch);
+	uint64_t v = vclock_get(&limbo->promote_term_map, replica_id);
+	bool res = v < limbo->promote_greatest_term;
+	latch_unlock(&limbo->promote_latch);
+	return res;
 }
 
 /**
@@ -300,7 +312,37 @@ txn_limbo_ack(struct txn_limbo *limbo, uint32_t replica_id, int64_t lsn);
 int
 txn_limbo_wait_complete(struct txn_limbo *limbo, struct txn_limbo_entry *entry);
 
-/** Execute a synchronous replication request. */
+/**
+ * Initiate execution of a synchronous replication request.
+ */
+static inline void
+txn_limbo_begin(struct txn_limbo *limbo)
+{
+	limbo->promote_latch_cnt++;
+	latch_lock(&limbo->promote_latch);
+}
+
+/** Commit a synchronous replication request. */
+static inline void
+txn_limbo_commit(struct txn_limbo *limbo)
+{
+	latch_unlock(&limbo->promote_latch);
+	limbo->promote_latch_cnt--;
+}
+
+/** Rollback a synchronous replication request. */
+static inline void
+txn_limbo_rollback(struct txn_limbo *limbo)
+{
+	latch_unlock(&limbo->promote_latch);
+}
+
+/** Apply a synchronous replication request after processing stage. */
+void
+txn_limbo_apply(struct txn_limbo *limbo,
+		const struct synchro_request *req);
+
+/** Process a synchronous replication request. */
 void
 txn_limbo_process(struct txn_limbo *limbo, const struct synchro_request *req);
 
-- 
2.31.1



More information about the Tarantool-patches mailing list